acm-header
Sign In

Communications of the ACM

ACM TechNews

Could a Pen Change How We Diagnose Brain Function?


View as: Print Mobile App Share:
Drawings by a healthy person (left) and by patients in the early stages of cognitive disorders.

Coupled with a digital pen, new models from the Massachusetts Institute of Technology Computer Science and Artificial Intelligence Lab can help detect dementia and other cognitive disorders earlier than ever before.

Credit: MIT Computer Science and Artificial Intelligence Lab

Researchers from the Massachusetts Institute of Technology's Computer Science and Artificial Intelligence Lab (CSAIL) have used artificial intelligence (AI) and a digital pen to diagnose dementia earlier than ever before.

Dementia screening via the Clock Drawing Test (CDT) has been a standard practice for some time, but its limitations and subjectivity spurred the researchers to use the camera-equipped Anoto Live Pen, which measures its position on the paper more than 80 times a second, enabling the system to analyze every single movement and pause by a subject. CSAIL and Lahey Hospital and Medical Center collaborated on software for analyzing this version of the test, with the end result being the digital Clock Drawing Test (dCDT).

The testers discovered their machine-learning computational models were much more accurate than standard models in diagnosing the presence and the precise nature of a cognitive impairment.

"We've improved the analysis so that it is automated and objective," notes MIT professor Cynthia Rudin. "With the right equipment, you can get results wherever you want, quickly, and with higher accuracy."

The researchers' next step is development of an interface to ease use of the dCDT technology by neurologists and non-specialists in hospitals.

From MIT News
View Full Article

 

Abstracts Copyright © 2015 Information Inc., Bethesda, Maryland, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account